Update milvus.yaml params (#377)

Signed-off-by: Bennu-Li <yunmei.li@zilliz.com>

Signed-off-by: Bennu-Li <yunmei.li@zilliz.com>

Author: Bennu-Li

charts/milvus/Chart.yaml

@@ -3,7 +3,7 @@ name: milvus
 appVersion: "2.1.4"
 kubeVersion: "^1.10.0-0"
 description: Milvus is an open-source vector database built to power AI applications and vector similarity search.
-version: 3.2.9
+version: 3.2.10
 keywords:
   - milvus
   - elastic

charts/milvus/templates/config.tpl

@@ -419,6 +419,9 @@ quotaAndLimits:
       dataNodeMemoryHighWaterLevel: {{ .Values.quotaAndLimits.limitWriting.memProtection.dataNodeMemoryHighWaterLevel }}
       queryNodeMemoryLowWaterLevel: {{ .Values.quotaAndLimits.limitWriting.memProtection.queryNodeMemoryLowWaterLevel }}
       queryNodeMemoryHighWaterLevel: {{ .Values.quotaAndLimits.limitWriting.memProtection.queryNodeMemoryHighWaterLevel }}
+    diskProtection:
+      enabled: {{ .Values.quotaAndLimits.limitWriting.diskProtection.enabled }}
+      diskQuota: {{ .Values.quotaAndLimits.limitWriting.diskProtection.diskQuota }}
 
   limitReading:
     forceDeny: {{ .Values.quotaAndLimits.limitReading.forceDeny }}
@@ -427,6 +430,11 @@ quotaAndLimits:
       enabled: {{ .Values.quotaAndLimits.limitReading.queueProtection.enabled }}
       nqInQueueThreshold: {{ .Values.quotaAndLimits.limitReading.queueProtection.nqInQueueThreshold }}
       queueLatencyThreshold: {{ .Values.quotaAndLimits.limitReading.queueProtection.queueLatencyThreshold }}
-      coolOffSpeed: {{ .Values.quotaAndLimits.limitReading.queueProtection.coolOffSpeed }}
+
+    resultProtection:
+      enabled: {{ .Values.quotaAndLimits.limitReading.resultProtection.enabled }}
+      maxReadResultRate: {{ .Values.quotaAndLimits.limitReading.resultProtection.maxReadResultRate }}
+
+    coolOffSpeed: {{ .Values.quotaAndLimits.limitReading.coolOffSpeed }}
 
 {{- end }}

charts/milvus/values.yaml

@@ -179,38 +179,38 @@ quotaAndLimits:
 
   ddl:  # ddl limit rates, default no limit.
     enabled: false
-    collectionRate:  # qps, default no limit, rate for CreateCollection, DropCollection, LoadCollection, ReleaseCollection
-    partitionRate:  # qps, default no limit, rate for CreatePartition, DropPartition, LoadPartition, ReleasePartition
+    collectionRate: -1  # qps, default no limit, rate for CreateCollection, DropCollection, LoadCollection, ReleaseCollection
+    partitionRate: -1  # qps, default no limit, rate for CreatePartition, DropPartition, LoadPartition, ReleasePartition
 
   indexRate:
     enabled: false
-    max:  # qps, default no limit, rate for CreateIndex, DropIndex
+    max: -1  # qps, default no limit, rate for CreateIndex, DropIndex
   flushRate:
     enabled: false
-    max:  # qps, default no limit, rate for flush
+    max: -1  # qps, default no limit, rate for flush
   compactionRate:
     enabled: false
-    max:  # qps, default no limit, rate for manualCompaction
+    max: -1  # qps, default no limit, rate for manualCompaction
 
   # dml limit rates, default no limit.
   # The maximum rate will not be greater than `max`.
   dml:
     enabled: false
     insertRate:
-      max:  # MB/s, default no limit
+      max: -1  # MB/s, default no limit
     deleteRate:
-      max:  # MB/s, default no limit
+      max: -1  # MB/s, default no limit
     bulkLoadRate:  # not support yet. TODO: limit bulkLoad rate
-      max:  # MB/s, default no limit
+      max: -1  # MB/s, default no limit
 
   # dql limit rates, default no limit.
   # The maximum rate will not be greater than `max`.
   dql:
     enabled: false
     searchRate:
-      max:  # vps (vectors per second), default no limit
+      max: -1  # vps (vectors per second), default no limit
     queryRate:
-      max:  # qps, default no limit
+      max: -1  # qps, default no limit
 
   # limitWriting decides whether dml requests are allowed.
   limitWriting:
@@ -233,6 +233,10 @@ quotaAndLimits:
       dataNodeMemoryHighWaterLevel: 0.95  # (0, 1], memoryHighWaterLevel in DataNodes
       queryNodeMemoryLowWaterLevel: 0.85  # (0, 1], memoryLowWaterLevel in QueryNodes
       queryNodeMemoryHighWaterLevel: 0.95  # (0, 1], memoryHighWaterLevel in QueryNodes
+    diskProtection:
+      # When the total file size of object storage is greater than `diskQuota`, all dml requests would be rejected;
+      enabled: true
+      diskQuota: -1  # GB, (0, +inf), default no limit
 
   # limitReading decides whether dql requests are allowed.
   limitReading:
@@ -245,16 +249,23 @@ quotaAndLimits:
       # nqInQueueThreshold indicated that the system was under backpressure for Search/Query path.
       # If NQ in any QueryNode's queue is greater than nqInQueueThreshold, search&query rates would gradually cool off
       # until the NQ in queue no longer exceeds nqInQueueThreshold. We think of the NQ of query request as 1.
-      nqInQueueThreshold:  # int, default no limit
+      nqInQueueThreshold: -1  # int, default no limit
 
       # queueLatencyThreshold indicated that the system was under backpressure for Search/Query path.
       # If dql latency of queuing is greater than queueLatencyThreshold, search&query rates would gradually cool off
       # until the latency of queuing no longer exceeds queueLatencyThreshold.
       # The latency here refers to the averaged latency over a period of time.
-      queueLatencyThreshold:  # milliseconds, default no limit
+      queueLatencyThreshold: -1  # milliseconds, default no limit
+
+    resultProtection:
+      enabled: false
+      # maxReadResultRate indicated that the system was under backpressure for Search/Query path.
+      # If dql result rate is greater than maxReadResultRate, search&query rates would gradually cool off
+      # until the read result rate no longer exceeds maxReadResultRate.
+      maxReadResultRate: -1  # MB/s, default no limit
 
-      # coolOffSpeed is the speed of search&query rates cool off.
-      coolOffSpeed: 0.9  # (0, 1]
+    # coolOffSpeed is the speed of search&query rates cool off.
+    coolOffSpeed: 0.9  # (0, 1]
 
 standalone:
   replicas: 1  # Run standalone mode with replication disabled